Assessment of Lung Diseases from Features Extraction of Breath Sounds Using Digital Signal Processing Methods

Abstract

Air movement through the respiratory system generates sound commonly known as breath sounds or Lung sounds (LS). Auscultation can detect abnormalities in airflow in the respiratory system, which is caused by lung diseases. Change in airflow patterns can also change the sounds generated in the respiratory process, causing abnormal or adventitious Lung sounds. Traditional analog auditory stethoscopes require profound concentration by expert physicians and acquired data can't be stored. In this paper, a non-invasive, non-hazardous way of collecting and analyzing lung sounds by the Digital signal processing (DSP) method is proposed. Lung sounds collected by the auscultation process were then digitized. Various features (Rms, Zero Crossings, Turn Count, Mean, Variance, Form Factor) were extracted from the digitized data stream using DSP methods. The developed system uses significant components like-(1) traditional listening, (2) visual presentation of raw data, and (3) extracted features using DSP methods, which then can be used for assessment of lung diseases.